Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to technological advancements

    oai_token-act-pair · gpt-3.5-turbo

    the word "and" frequently appearing in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odcast
    -0.56
    :(
    -0.55
    ":""},{"
    -0.54
    ESE
    -0.53
    omi
    -0.52
    éŃĶ
    -0.51
    hov
    -0.51
    wic
    -0.51
    fur
    -0.50
    DX
    -0.49
    POSITIVE LOGITS
     consequently
    0.99
     thus
    0.94
     hence
    0.93
     therefore
    0.92
     thereby
    0.90
     then
    0.79
     possibly
    0.78
     vice
    0.78
    rogens
    0.74
     thence
    0.73
    Act Density 0.882%

    No Known Activations